Fred
> -----Original Message-----
> From: owner-linux-kernel@vger.rutgers.edu
> [mailto:owner-linux-kernel@vger.rutgers.edu]On Behalf Of Heinz
> Mauelshagen
> Sent: Thursday, January 14, 1999 1:02 PM
> To: Andrea Arcangeli
> Cc: mge@ts1.ez-darmstadt.telekom.de; linux-kernel@vger.rutgers.edu
> Subject: Re: [patch] arca-vm-19 [Re: Results: Zlatko's new vm patch]
>
>
> >
> > On Wed, 13 Jan 1999, Andrea Arcangeli wrote:
> >
> > > I produced a new arca-vm-19. I would like if you could
> try it. I don't
> >
> > It seems that the better algorithm I am be able to invent
> is been the
> > growing_swap_cache one (the one in arca-vm-16). Steve could
> you try this
> > new patch (arca-vm-20) against real 2.2.0-pre7? I think
> that it should be
> > still better than arca-vm-16 + SWAP_CLUSTER_MAX=512.
> >
> > If it will be not very good could you do:
> >
> > echo 8 2 4 512 512 512 > /proc/sys/vm/pager
> >
> > and try again? (such numbers should be the same of setting
> > SWAP_CLUSTER_MAX in arca-vm-16, but as default only the
> max_async_pages is
> > set to 512 because I think it's been the only one that made
> a difference).
> >
> > If this will be not the best again you could apply the
> filemap.c patch I
> > sent you in the last email (the one that return to put the
> shrink_mmap()
> > weight exponential increasing in function of priority) and
> try again?
> >
>
> Hi Andrea!
>
> I tested vm20 against bare 2.2.0-pre7 and it doesn't do the job 8*(
>
>
> The system is a little bit more responsive while doing a 12G mke2fs
> now only taking about 10-20 seconds ;-( to bring up another kvt
> compared to end of mke2fs without vm20.
>
> But compared to < 2.2.0 VM this is about at least 10-20!!!
> times slower.
>
>
> The system (2*PII/350, 256M RAM) swaps out 30MB (kvts etc.) for _no_
> obvious reason with paging rates up to > 100/s ?!
>
> I don't like 1 process eating up main memory for buffer/page cache
> _and_ thereby causing swaping out inactive others.
>
> Other testers reported the same effect, if the system runs
> for some days under medium load.
>
> /proc,sys/vm/{buffermemm, pagecache} are gone now because
> they haven't been
> used any longer, but at least i liked them.
>
> Why not keep that interface and the thereby implied limits in
> the kernel
> VM to allow the admin to set them to 100% if he likes to?
>
> Sorry if this sounds too bad, but to my opinion this
> behaviour is an absolute
> _must_ change before the final 2.2 release!
>
> Keep up the good work,
> Heinz
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/